State recognition method for machining process of a large spot welder based on improved genetic algorithm and hidden Markov model

Abstract

Large spot welder is an important equipment in rail transit equipment manufacturing industry, but having the problem of low utilization rate and low effectlvely machining rate. State monitoring can master its operating states real time and comprehensively, and providing data support for state recognition. Hidden Markov model is a state classification method, but it is sensitive to the initial model parameters and easy to trap into a local optima. Genetic algorithm is a global searching method; however, it is quite poor at hill climbing and also has the problem of premature convergence. In this paper, proposing the improved genetic algorithm, and combining improved genetic algorithm and hidden Markov model, a new method of state recognition method named improved genetic algorithm–hidden Markov model is proposed. In the proposed method, improved genetic algorithm is used for optimizing the initial parameters, and hidden Markov model as a classifier to recognize the operating states for machining process. This method is also compared with the other two recognition methods named adaptive genetic algorithm–hidden Markov model and hidden Markov model, in which adaptive genetic algorithm is similarly used for optimizing the initial parameters, however hidden Markov model (in both methods) as a classifier. Experimental results show that the proposed method is very effective, and the improved genetic algorithm–hidden Markov model recognition method is superior to the adaptive genetic algorithm–hidden Markov model and hidden Markov model recognition method.

Keywords

Large spot welder state recognition improved genetic algorithm hidden Markov model

Get full access to this article

View all access options for this article.

References

Bereta

Pedrycz

Reformat

. Local descriptors and similarity measures for frontal face recognition: a comparative analysis. J Vis Commun Image Represent 2013; 24: 1213–1231.

Zhang M and Liu S J. A model analysis method of cognitive radio based on game theory. In: 2010 IEEE International Conference on Future Computer and Communication (ICFCC), Wuhan, China, 2010, vol. 2, pp.833–836.

Hernandez-Lobato

Suarez

. Network-based sparse Bayesian classification. Pattern Recognit 2011; 44: 886–900.

Jiang

Zhang

. A novel distance function frequency difference metric. Int J Pattern Recognit Artif Intell 2014; 28: 1451002–1451002.

Fang

. Expert system-supported fuzzy diagnosis of finish-turning process states. Int J Mach Tools Manuf 1995; 35: 913–924.

Chen YL and Zhang TJ. Research on the application of Fuzzy Fault Tree analysis method in the machinery equipment fault diagnosis. In: 2010 IEEE International Asia Conference on Informatics in Control, Automation and Robotics(CAR), Wuhan, China, 2010, vol. 1, pp.84–87.

Ting

Yong

Mirhassani

. Self-adjustable neural network for speech recognition. Eng Appl Artif Intell 2013; 26: 2022–2027.

Zhang

Liu

Wang

ZZJ

. Evaluation of a set of new ORF kernel functions of SVM for speech recognition. Eng Appl Artif Intell 2013; 26: 2574–2580.

Huang

Jack

. Semi-continuous hidden Markov models for speech signals. Comput Speech Language 1989; 3: 239–251.

10.

Boutros

Liang

. Detection and diagnosis of bearing and cutting tool faults using hidden Markov models. Mech Syst Signal Process 2011; 25: 2102–2124.

11.

Geramifard

Panda

. Fault detection and diagnosis in synchronous motors using hidden Markov model-based semi-nonparametric approach. Eng Appl Artif Intell 2013; 26: 1919–1929.

12.

Fang

Xia

. Increasing mapping based hidden Markov model for dynamic process monitoring and diagnosis. Expert Syst Appl 2014; 41: 744–751.

13.

Zhu

Wong

Hong

. Multi-category micro-milling tool wear monitoring with continuous hidden Markov models. Mech Syst Signal Process 2009; 23: 547–560.

14.

. A nonlinear probabilistic method and contribution analysis for machine condition monitoring. Mech Syst Signal Process 2013; 37: 293–314.

15.

Yan

Kong

. Machine condition monitoring using principal component representations. Mech Syst Signal Process 2009; 23: 446–466.

16.

Widodo

Yang

. Support vector machine in machine condition monitoring and fault diagnosis. Mech Syst Signal Process 2007; 21: 2560–2574.

17.

Elbhbah

Sinha

. Vibration-based condition monitoring of rotating machines using a machine composite spectrum. J Sound Vib 2013; 332: 2831–2845.

18.

Bhattacharyya

Sengupta

Mukhopadhyay

. On-line tool condition monitoring in face milling using current and power signals. Int J Prod Res 2008; 46: 1187–2101.

19.

Rabiner

. A tutorial on hidden Markov models and selected applications in speech recognition. Proc IEEE 1989; 2: 257–285.

20.

Srinivas

Patnaik

. Genetic algorithm: a survey. IEEE Comput 1994; 27: 17–26.

21.

Chau

Kwong

Diu

. Optimization of HMM by a genetic algorithm. Acoust Speech Signal Process ICASSP (1997) 1997; 3: 1727–1730.

22.

Kwong

Chau

Man

. Optimisation of HMM topology and its model parameters by genetic algorithms. Pattern Recognit 2001; 34: 509–522.

23.

Bhowmik

Parui

Kar

. HMM parameter estimation with genetic algorithm for handwritten word recognition. Pattern Recognit Mach Intell 2007; 4815: 536–544.

24.

Kwong

. Genetic algorithm based simultaneous optimization of feature subsets and hidden Markov model parameters for discrimination between speech and non-speech events. Int J Speech Technol 2010; 13: 61–73.

25.

Makhlouf

Lazli

Bensaker

. Automatic speech reading using genetic hybridization of hidden Markov models. Comput Inform Technol WCCIT 2013, pp. 1–6.

26.

Kou

. The basic theory and application of genetic algorithm, Beijing: Science Press, 2003.

27.

Lei

Zhang

. MATLAB genetic algorithm toolbox and applications, 2nd ed. Xi’an: Xi’an University of Electronic Science and Technology Press, 2004.

28.

Chen

Liang

Hong

. Forecasting holiday daily tourist flow based on seasonal support vector regression with adaptive genetic algorithm. Appl Soft Comput 2015; 26: 435–443.